def sample_b_to_rate(R):
"""
The b in this function name means branch.
@param R: directed topology
@return: a sampled map from vertex to expected rate
"""
b_to_rate = {}
v_to_source = Ftree.R_to_v_to_source(R)
for v in Ftree.R_to_preorder(R):
p = v_to_source.get(v, None)
if p is None:
continue
# sample a coefficient regardless of whether we use it
# this is an obsolete method
#log_coeff = (random.random() - 0.5) * epsrate
#coeff = math.exp(log_coeff)
curr_branch = frozenset([v, p])
gp = v_to_source.get(p, None)
if gp is None:
parent_rate = 1.0
else:
prev_branch = frozenset([p, gp])
parent_rate = b_to_rate[prev_branch]
b_to_rate[curr_branch] = random.expovariate(1/parent_rate)
return b_to_rate
def sample_brownian_motion(R, B):
"""
Sample brownian motion on a tree.
@param R: directed tree
@param B: branch lengths
@return: map from vertex to sample
"""
r = Ftree.R_to_root(R)
v_to_sample = {r: 0}
v_to_sinks = Ftree.R_to_v_to_sinks(R)
for v in Ftree.R_to_preorder(R):
for sink in v_to_sinks[v]:
u_edge = frozenset((v, sink))
mu = v_to_sample[v]
var = B[u_edge]
v_to_sample[sink] = random.gauss(mu, math.sqrt(var))
return v_to_sample
def sample_jc_column(R, B):
"""
Sample a column of a Jukes-Cantor alignment.
@param R: Ftree directed topology
@param B: branch lengths in expected number of substitutions
@return: a map from vertex to nucleotide
"""
acgt = 'ACGT'
v_to_nt = {}
v_to_source = Ftree.R_to_v_to_source(R)
for v in Ftree.R_to_preorder(R):
p = v_to_source.get(v, None)
if p is None:
v_to_nt[v] = random.choice(acgt)
else:
d = B[frozenset([v, p])]
p_randomize = 1.0 - math.exp(-(4.0 / 3.0) * d)
if random.random() < p_randomize:
v_to_nt[v] = random.choice(acgt)
else:
v_to_nt[v] = v_to_nt[p]
return v_to_nt